Skip to content
Contentful MCP Server

Contentful MCP Server

Released
2 views
v1.15.0
MIT

Summary

Contentful's official MCP server — model content types, search and edit entries, manage assets and publish, with semantic vector search over your space.

Features

  • Full content-type lifecycle: create, update, publish, unpublish, delete
  • Entry search, filtering, editing and publishing
  • Semantic vector search across entries
  • Entry version history via snapshots
  • Asset, space and environment management
  • get_initial_context primes the agent with the space's shape before it acts

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

  1. Open your agent's MCP configuration file.
  2. Merge the snippet below into it, filling in the environment variables with your own values.
  3. Restart the agent — the "Contentful MCP Server" tools will be available.
{
  "mcpServers": {
    "contentful-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@contentful/mcp-server"
      ],
      "env": {
        "CONTENTFUL_MANAGEMENT_ACCESS_TOKEN": "<your-CMA-token>",
        "SPACE_ID": "<your-space-id>",
        "ENVIRONMENT_ID": "master",
        "CONTENTFUL_HOST": "api.contentful.com"
      }
    }
  }
}

Description

Contentful's official MCP server exposes the Content Management API as tools, so an agent can do the content-operations work that normally means clicking through the web app or writing a one-off migration script.

Coverage
  • Content types — list, inspect, create, update, publish, unpublish and delete. This is the part that turns "add a subtitle field to the blog post model across environments" into one request.
  • Entries — search and filter, retrieve, create, update, publish and delete, plus get_entry_snapshot for version history when you need to see what a field held before someone changed it.
  • Semantic searchsemantic_search finds entries by meaning rather than keyword, which matters in a space where the same concept is worded five different ways across a few thousand entries.
  • Assets, spaces and environments — the surrounding management surface.

get_initial_context runs first and gives the agent the space's shape and usage instructions before it starts making calls, which is why it behaves sensibly on an unfamiliar space.

Setup

Runs locally over stdio as npx -y @contentful/mcp-server, configured with CONTENTFUL_MANAGEMENT_ACCESS_TOKEN, SPACE_ID and ENVIRONMENT_ID (master unless you are working elsewhere). CONTENTFUL_HOST switches between api.contentful.com and the EU endpoint.

A word of caution

The token this server takes is a Content Management token — it can delete content types and unpublish live entries. Point it at a sandbox environment before pointing it at master, and treat the environment ID as the safety rail it is.

MIT licensed, maintained by Contentful.

Related MCP Servers

MCP: Engram

by Gentleman Programming

New

Persistent memory for coding agents as a single Go binary — SQLite and FTS5 behind MCP, an HTTP API, a CLI and a TUI, with no Node, Python or Docker required.

MCP: agent-device

by Callstack

New

Give a coding agent a live feedback loop on real mobile, TV and desktop apps — inspect, tap, type and capture evidence on iOS, Android and HarmonyOS over MCP or a CLI.

New

The official W&B MCP server: query experiment runs, Weave LLM traces, artifacts and registries in natural language, and write findings back as a W&B report.

Featured

Replicate's official MCP server: search thousands of hosted models, read their schemas, and run predictions on image, video, audio and language models from inside an agent.

Browse all MCP servers →